Tabherd
Provides tools for controlling the Brave browser via an extension and local native bridge, enabling tab organization, window movement, bookmark saving, page reading, and browser interaction.
Provides tools for controlling the Firefox browser via an extension and local native bridge, enabling tab organization, window movement, bookmark saving, page reading, and browser interaction.
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
Tabherd
Your browser, connected to your agent. A thin extension and local native bridge expose browser APIs through six MCP tools and a JSON CLI. Organize tabs, move windows, save bookmarks, read pages, and interact with the browser you already use.
Quick start
Requires Node.js 22.18 or newer.
npm install -g tabherdDownload
tabherd-VERSION-chrome.zipfrom the latest release and unzip it. Load the folder as an unpacked extension in Chrome, Chromium, Edge, or Brave (Developer mode → Load unpacked).Register the host for every installed browser:
tabherd setup.Reload the extension and check its popup connection.
Run
tabherd doctor, thentabherd call tabs.query '[{}]'.
For Firefox, download tabherd-VERSION-firefox.zip and temporarily load its manifest.json from about:debugging.
On Nix, nix run github:lmdevv/tabherd -- --help runs the CLI. The NixOS and Home Manager modules (programs.tabherd.enable = true) register the browsers declaratively, so you skip tabherd setup. See Nix and NixOS.
Add the bridge to your agent’s stdio MCP configuration:
{
"mcpServers": {
"tabherd": {
"command": "tabherd",
"args": ["mcp"]
}
}
}The browser starts the native host automatically. No account or separate server. Tabherd grants local control of your real browser profile; use it with agents you trust, and pick Full access, Standard (no cookies, page JavaScript, or data deletion) or Read only in the extension popup. API availability varies by browser.
Quick start · Nix and NixOS · Tools and CLI · Agent skill
Related MCP server: Pagewright (browser-mcp)
From source
Requires pnpm.
pnpm install
pnpm buildLoad apps/extension/dist/chrome-mv3 as an unpacked extension, then use node packages/bridge/dist/index.js in place of tabherd. Firefox: pnpm build:firefox, then load apps/extension/dist/firefox-mv2/manifest.json.
Docs: pnpm --filter docs dev. Checks: pnpm test and pnpm check-types. Optional real browser test on Linux with Chromium: pnpm test:browser.
License
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Browz hosted MCP (free public beta): let an AI app drive your own Browz browser profiles from anywhere. Connect https://mcp.gobrowz.com/mcp and sign in with your Browz account (OAuth) or an agent token. Each call is relayed to the Browz app on your computer, which must be online with Remote control on and have a hardware security chip (Mac Secure Enclave or TPM 2.0). 17 tools: profiles, tabs, navigate, snapshot, act, wait, screenshot. Cookies, downloads and stored sign-ins stay on your computer.
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
Whole browser tasks done in pilotfish's cloud for any MCP agent, signed in with your saved logins.
Stealth web browser for agents: search, fetch, click, download and type in persistent MCP sessions.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceMCP server for local browser control via Chrome/Edge extension, enabling agents to open isolated tabs, observe pages, take screenshots, and interact with accessible controls using an existing browser profile. It is agent-agnostic, local-only, and supports safe session scoping with origin grants and sensitive-data blocking.MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to see and control the user's real Chrome/Brave/Edge profile over MCP, so they can read pages, click, type, take screenshots, audit layouts, debug CSS, and scrape paginated or infinite-scroll data. Because it drives the normal browser via the DevTools protocol with real input events, it works on modern JavaScript apps and on sites where the user is logged in.17 npm1MIT
- AlicenseNot gradedqualityBmaintenanceEnables an AI agent to read and operate the Chrome or Edge tabs you are already using — titles, URLs, text, HTML, screenshots, clicks, typing, scrolling, and tab management — via a browser extension and native messaging, without restarting the browser, switching profiles, or opening a debug port. It exposes these capabilities as 19 MCP tools, with access limited to explicitly shared tabs and hardened by per-tab, origin-bound grants plus domain allow/deny lists.2MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP agents to drive the user's already-open Chrome profile through a Manifest V3 extension and loopback bridge, listing and controlling existing tabs, capturing screenshots, and sending clicks, typing, drags and key holds via an independent on-page cursor without moving the system mouse. It also supports form filling, console and network inspection, read-only or confirmed JavaScript execution, file and PDF downloads, and game-style screenshot/action loops with snapshot recovery and an emergency stop.MIT